Machine learning-assisted optimization of NbTa alloy coating thickness via DC magnetron sputtering for SS316L bipolar plates in PEMFCs
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Corrosion and high interfacial contact resistance (ICR) in metallic bipolar plates (BPPs) remain critical challenges limiting the durability of proton exchange membrane fuel cells (PEMFCs). This study employs a dual experimental-machine learning (ML) approach to optimize NbTa alloy coatings deposited on SS316L BPPs via DC-balanced magnetron sputtering. Electrochemical testing and surface characterization were conducted under simulated and accelerated PEMFC conditions, while an artificial neural network (ANN) model was developed to predict performance trends across coating thicknesses. A 2.5 μm coating exhibited the best overall performance, reducing corrosion current density to below 0.2 μA.cm -2 and ICR to 0.9 mΩ.cm 2 . Notably, the 1.7 μm coating also met U.S. DOE targets, representing a practical balance between cost and durability. The ANN model achieved high predictive accuracy (R 2 = 0.992), validating its use in guiding experimental optimization. A preliminary techno-economic assessment indicated that NbTa alloy coatings could achieve favorable payback periods of only a few years under plausible manufacturing scenarios, reinforcing their potential for large-scale PEMFC deployment. This integrated experimental-ML framework offers a powerful strategy for accelerating the development of corrosion-resistant, conductive coatings tailored for advanced PEMFC applications. Highlights : • Developed NbTa alloy coated SS316L bipolar plates for PEM fuel cells. • NbTa alloy coated SS316L improved corrosion potential and reduced corrosion current. • NbTa alloy coated SS316L lowered interfacial contact resistance and enhanced durability. • Increasing alloy coated thickness improved performance and met all DOE standards. • Developed machine learning models for predicting anti-corrosion coating performance. • ANN models with dropout achieved R 2 > 0.99 in predicting imaginary impedance parameters.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it